prediction claim
A superficial reward signal, such as whether a user accepts a code edit, might be reward-hacked.
John Schulman · AI researchers debate how close we are to recursive self-improvement · 11 Sept 2026
In their words
The transcript segments this claim was taken from
“And if you use some kind of superficial signal, like did they accept the code,”
“the edit,”
“that might get reward hacked in some way.”Play from 45:13Report a misattribution
65%how strongly it was put, not whether it is true
75%importance to the conversation
98%confidence the claim was read correctly